Autonome Mobile Systeme 2005
DOI: 10.1007/3-540-30292-1_11
|View full text |Cite
|
Sign up to set email alerts
|

Segmentation of Independently Moving Objects Using a Maximum-Likelihood Principle

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Publication Types

Select...
2
2
1

Relationship

2
3

Authors

Journals

citations
Cited by 5 publications
(4 citation statements)
references
References 6 publications
0
4
0
Order By: Relevance
“…Outlier detection. To detect outliers in ego-motion estimation, in particular IMOs, several methods were suggested, namely frameworks employing the EM algorithm [15,5], the Collinear Point Constraint [12] and the RANSAC algorithm [19]. In accordance to the conclusion of Torr's thesis, who found that the RANSAC algorithm performs best in motion segmentation and outlier detection, we chose RANSAC to achieve robust ego-motion estimation.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Outlier detection. To detect outliers in ego-motion estimation, in particular IMOs, several methods were suggested, namely frameworks employing the EM algorithm [15,5], the Collinear Point Constraint [12] and the RANSAC algorithm [19]. In accordance to the conclusion of Torr's thesis, who found that the RANSAC algorithm performs best in motion segmentation and outlier detection, we chose RANSAC to achieve robust ego-motion estimation.…”
Section: Discussionmentioning
confidence: 99%
“…A key functionality of the subspace method is the possibility to cluster ego-motion and motion of IMOs. More robust approaches assume noisy flow estimates besides IMOs when estimating ego-motion with the EM algorithm [16,5]. Generally, the EM algorithm uses an iterative computational scheme and in each iteration the evaluation of the method estimating ego-motion is required.…”
Section: Motivationmentioning
confidence: 99%
“…Other methods solve segmentation and heading estimation with the expectation and maximization (EM) algorithm (MacLean et al, 1994; Clauss et al, 2005). The expectation step estimates the probability of a data point as being generated by a motion model.…”
Section: Discussionmentioning
confidence: 99%
“…Existing motion detection schemes exploit a subset of the above constraints either directly or indirectly. A popular scheme is the angle criterion [8,24] which uses the direction of optical flow vectors. When moving purely translational toward the scene, all flow vectors are parallel to the corresponding epipolar lines and point away from the epipole (focus of expansion).…”
Section: Monocular Visionmentioning
confidence: 99%